Add Qwen3.5-397B INT4-AutoRound TP=4 recipe and Marlin fix

Production-tested recipe for running Qwen3.5-397B-A17B with INT4 AutoRound
quantization across 4 DGX Spark nodes using tensor parallelism.

Performance (4× DGX Spark, driver 580.126.09):
- Single user: 37 tok/s
- 4 concurrent: ~26 tok/s per user, ~103 tok/s aggregate

The Marlin TP fix resolves the MIN_THREAD_N=64 constraint that breaks
in_proj_ba layers at TP=4 (output_size=128/4=32 < 64). Solution:
ReplicatedLinear for B/A projections, applied via diff patches.

Key config:
- VLLM_MARLIN_USE_ATOMIC_ADD=1 (required for Marlin correctness)
- KV cache FP8, prefix caching enabled
- gpu_memory_utilization 0.78 (UMA safe margin)
- CUDAGraphs enabled (default, requires driver 580.x)

Note: Driver 590.x has CUDAGraph capture deadlock on GB10 unified memory.
Stay on driver 580.126.09.

mods/fix-qwen35-tp4-marlin/fix_rope.py

@@ -0,0 +1,23 @@
+# Fix: ignore_keys_at_rope_validation is a list but transformers uses | (set union)
+import re
+
+path = "/usr/local/lib/python3.12/dist-packages/vllm/transformers_utils/configs/qwen3_5_moe.py"
+with open(path) as f:
+    content = f.read()
+
+old = """kwargs["ignore_keys_at_rope_validation"] = [
+            "mrope_section",
+            "mrope_interleaved",
+        ]"""
+
+new = """kwargs["ignore_keys_at_rope_validation"] = {
+            "mrope_section",
+            "mrope_interleaved",
+        }"""
+
+content = content.replace(old, new)
+
+with open(path, "w") as f:
+    f.write(content)
+
+print("Fixed ignore_keys_at_rope_validation: list -> set")